[Android speech synthesis TTS] mainstream domestic engine comparison, androidtts

[Android speech synthesis TTS] mainstream domestic engine comparison, androidtts
PS.

TTS is TextToSpeech (from text to language), that is, speech synthesis. TTS intelligently converts text into natural speech streams. TTS technology converts text files in real time. The conversion time can be calculated in seconds. With its unique Intelligent Voice controller, the voice and audio laws of text output are smooth, making the listener feel natural when listening to information, and there is no indifference or cool sense of machine speech output.

Throughout the application market, we will find that more and more apps contain speech recognition and speech synthesis functions. TTS can help developers easily build various speech interaction applications and help industry partners build special speech service products.

Next we will analyze the mainstream voice engine providers in China, hoping to help you develop and select the appropriate products:

Provider	Whether to provide offline TTS	Charged or not	Synthesis Quality
KEDA xunfei	Yes	Yes	Good
Yun Zhisheng	Yes	No	Average
Baidu	No	No	Better

KEDA xunfei voice:

Xunfei voice can be called the Domestic voice giant, because its early speech recognition technology is also relatively leading, so its access price is also relatively high. Currently, xunfei does not have free TTS. If you need access, you have to purchase it.

Yun Zhisheng

Yun Zhisheng was founded in 2012. Although it has only experienced more than one year of development, its core team of speech recognition technology has been working for more than ten years and has accumulated a wealth of experience, this is also why we have been able to do well in the speech recognition field in just one year. Micro-speech plug-in, sogou voice assistant, Leeco super TV, old Luo hammer operating system, touchpal input method, and Netease + Telecom launched Yixin, which uses the voice recognition of yunzhi. In 2013, Yun Zhisheng received a high degree of recognition in the capital market and was highly sought after.

Currently, Apsara stack provides free offline TTS, but it has few APIs, simple functions, and rigid speech synthesis. If you do not have high requirements for speech synthesis, you can consider accessing it.

Baidu voice:

Relying on Baidu open cloud, Baidu speech provides industry-leading, permanently free voice technology services to partners. Currently, the services available include speech recognition, semantic parsing, and speech synthesis, in the future, we will continue to provide open resources, multi-round dialogs, and other technical services. Through sdks, REST APIs, and offline Development kits, we will meet the development needs of different developers.

Currently, Baidu speech provides free voice access, and the speech synthesis quality is acceptable, but offline TTS is not yet available.

Related reading:

[Android speech synthesis TTS] Baidu Speech Access Method and usage tips

[Android speech synthesis TTS] detailed description on offline TTS usage